Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S2992815AbXEBGSQ (ORCPT ); Wed, 2 May 2007 02:18:16 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S2992797AbXEBGSP (ORCPT ); Wed, 2 May 2007 02:18:15 -0400 Received: from mga03.intel.com ([143.182.124.21]:6235 "EHLO mga03.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S2992812AbXEBGSM (ORCPT ); Wed, 2 May 2007 02:18:12 -0400 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="4.14,477,1170662400"; d="scan'208";a="222855959" From: Dan Williams Subject: [PATCH 07/16] md: move write operations to raid5_run_ops To: neilb@suse.de, akpm@linux-foundation.org, christopher.leech@intel.com Cc: linux-kernel@vger.kernel.org, linux-raid@vger.kernel.org Date: Tue, 01 May 2007 23:18:11 -0700 Message-ID: <20070502061811.7066.16213.stgit@dwillia2-linux.ch.intel.com> In-Reply-To: <20070502060949.7066.357.stgit@dwillia2-linux.ch.intel.com> References: <20070502060949.7066.357.stgit@dwillia2-linux.ch.intel.com> User-Agent: StGIT/0.12.1 MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 6634 Lines: 197 handle_stripe sets STRIPE_OP_PREXOR, STRIPE_OP_BIODRAIN, STRIPE_OP_POSTXOR to request a write to the stripe cache. raid5_run_ops is triggerred to run and executes the request outside the stripe lock. Changelog: * make the 'rcw' parameter to handle_write_operations5 a simple flag, Neil Brown * remove test_and_set/test_and_clear BUG_ONs, Neil Brown Signed-off-by: Dan Williams --- drivers/md/raid5.c | 151 +++++++++++++++++++++++++++++++++++++++++++++------- 1 files changed, 130 insertions(+), 21 deletions(-) diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 14e9f6a..03a435d 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -1807,7 +1807,74 @@ static void compute_block_2(struct stripe_head *sh, int dd_idx1, int dd_idx2) } } +static int handle_write_operations5(struct stripe_head *sh, int rcw, int expand) +{ + int i, pd_idx = sh->pd_idx, disks = sh->disks; + int locked=0; + + if (rcw) { + /* skip the drain operation on an expand */ + if (!expand) { + set_bit(STRIPE_OP_BIODRAIN, &sh->ops.pending); + sh->ops.count++; + } + + set_bit(STRIPE_OP_POSTXOR, &sh->ops.pending); + sh->ops.count++; + + for (i=disks ; i-- ;) { + struct r5dev *dev = &sh->dev[i]; + + if (dev->towrite) { + set_bit(R5_LOCKED, &dev->flags); + if (!expand) + clear_bit(R5_UPTODATE, &dev->flags); + locked++; + } + } + } else { + BUG_ON(!(test_bit(R5_UPTODATE, &sh->dev[pd_idx].flags) || + test_bit(R5_Wantcompute, &sh->dev[pd_idx].flags))); + + set_bit(STRIPE_OP_PREXOR, &sh->ops.pending); + set_bit(STRIPE_OP_BIODRAIN, &sh->ops.pending); + set_bit(STRIPE_OP_POSTXOR, &sh->ops.pending); + + sh->ops.count += 3; + + for (i=disks ; i-- ;) { + struct r5dev *dev = &sh->dev[i]; + if (i==pd_idx) + continue; + /* For a read-modify write there may be blocks that are + * locked for reading while others are ready to be written + * so we distinguish these blocks by the R5_Wantprexor bit + */ + if (dev->towrite && + (test_bit(R5_UPTODATE, &dev->flags) || + test_bit(R5_Wantcompute, &dev->flags))) { + set_bit(R5_Wantprexor, &dev->flags); + set_bit(R5_LOCKED, &dev->flags); + clear_bit(R5_UPTODATE, &dev->flags); + locked++; + } + } + } + + /* keep the parity disk locked while asynchronous operations + * are in flight + */ + set_bit(R5_LOCKED, &sh->dev[pd_idx].flags); + clear_bit(R5_UPTODATE, &sh->dev[pd_idx].flags); + locked++; + + PRINTK("%s: stripe %llu locked: %d pending: %lx\n", + __FUNCTION__, (unsigned long long)sh->sector, + locked, sh->ops.pending); + + return locked; +} /* * Each stripe/dev can have one or more bion attached. @@ -2170,8 +2237,67 @@ static void handle_stripe5(struct stripe_head *sh) set_bit(STRIPE_HANDLE, &sh->state); } - /* now to consider writing and what else, if anything should be read */ - if (to_write) { + /* Now we check to see if any write operations have recently + * completed + */ + + /* leave prexor set until postxor is done, allows us to distinguish + * a rmw from a rcw during biodrain + */ + if (test_bit(STRIPE_OP_PREXOR, &sh->ops.complete) && + test_bit(STRIPE_OP_POSTXOR, &sh->ops.complete)) { + + clear_bit(STRIPE_OP_PREXOR, &sh->ops.complete); + clear_bit(STRIPE_OP_PREXOR, &sh->ops.ack); + clear_bit(STRIPE_OP_PREXOR, &sh->ops.pending); + + for (i=disks; i--;) + clear_bit(R5_Wantprexor, &sh->dev[i].flags); + } + + /* if only POSTXOR is set then this is an 'expand' postxor */ + if (test_bit(STRIPE_OP_BIODRAIN, &sh->ops.complete) && + test_bit(STRIPE_OP_POSTXOR, &sh->ops.complete)) { + + clear_bit(STRIPE_OP_BIODRAIN, &sh->ops.complete); + clear_bit(STRIPE_OP_BIODRAIN, &sh->ops.ack); + clear_bit(STRIPE_OP_BIODRAIN, &sh->ops.pending); + + clear_bit(STRIPE_OP_POSTXOR, &sh->ops.complete); + clear_bit(STRIPE_OP_POSTXOR, &sh->ops.ack); + clear_bit(STRIPE_OP_POSTXOR, &sh->ops.pending); + + /* All the 'written' buffers and the parity block are ready to be + * written back to disk + */ + BUG_ON(!test_bit(R5_UPTODATE, &sh->dev[sh->pd_idx].flags)); + for (i=disks; i--;) { + dev = &sh->dev[i]; + if (test_bit(R5_LOCKED, &dev->flags) && + (i == sh->pd_idx || dev->written)) { + PRINTK("Writing block %d\n", i); + set_bit(R5_Wantwrite, &dev->flags); + if (!test_and_set_bit(STRIPE_OP_IO, &sh->ops.pending)) + sh->ops.count++; + if (!test_bit(R5_Insync, &dev->flags) + || (i==sh->pd_idx && failed == 0)) + set_bit(STRIPE_INSYNC, &sh->state); + } + } + if (test_and_clear_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) { + atomic_dec(&conf->preread_active_stripes); + if (atomic_read(&conf->preread_active_stripes) < IO_THRESHOLD) + md_wakeup_thread(conf->mddev->thread); + } + } + + /* 1/ Now to consider new write requests and what else, if anything should be read + * 2/ Check operations clobber the parity block so do not start new writes while + * a check is in flight + * 3/ Write operations do not stack + */ + if (to_write && !test_bit(STRIPE_OP_POSTXOR, &sh->ops.pending) && + !test_bit(STRIPE_OP_CHECK, &sh->ops.pending)) { int rmw=0, rcw=0; for (i=disks ; i--;) { /* would I have to read this buffer for read_modify_write */ @@ -2238,25 +2364,8 @@ static void handle_stripe5(struct stripe_head *sh) } /* now if nothing is locked, and if we have enough data, we can start a write request */ if (locked == 0 && (rcw == 0 ||rmw == 0) && - !test_bit(STRIPE_BIT_DELAY, &sh->state)) { - PRINTK("Computing parity...\n"); - compute_parity5(sh, rcw==0 ? RECONSTRUCT_WRITE : READ_MODIFY_WRITE); - /* now every locked buffer is ready to be written */ - for (i=disks; i--;) - if (test_bit(R5_LOCKED, &sh->dev[i].flags)) { - PRINTK("Writing block %d\n", i); - locked++; - set_bit(R5_Wantwrite, &sh->dev[i].flags); - if (!test_bit(R5_Insync, &sh->dev[i].flags) - || (i==sh->pd_idx && failed == 0)) - set_bit(STRIPE_INSYNC, &sh->state); - } - if (test_and_clear_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) { - atomic_dec(&conf->preread_active_stripes); - if (atomic_read(&conf->preread_active_stripes) < IO_THRESHOLD) - md_wakeup_thread(conf->mddev->thread); - } - } + !test_bit(STRIPE_BIT_DELAY, &sh->state)) + locked += handle_write_operations5(sh, rcw == 0, 0); } /* maybe we need to check and possibly fix the parity for this stripe - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/